Jiangyun Li, Zhongkang Lu, Shuang Leng, Xiaohong Wang, Lohendran Baskaran, Min Sen Yew, Mark Chan, Lynette Ls Teo, Kee Yuan Ngiam, Hwee Kuan Lee, Liang Zhong, Zhiping Lin, Weimin Huang, "Hierarchical Auto-Labeling of Coronary Arteries on CT Coronary Angiography Images," 2024 46th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Orlando, USA, 2024, pp. 1-4
Abstract:
The auto-labeling of coronary artery segments
plays an important role in the diagnosis of cardiovascular
diseases. Due to the high degree of complexity and diversity
in coronary artery structures, it is still a very challenging task
after many years of exploration and study. In this paper, we
propose a hierarchical scheme based on PointNet++ models
and new topological structural features for automatic labeling
of coronary artery segments. The inputs are 3D coronary
artery centerline points extracted from CTCA images, and the
outputs are the correspondent label indexes. The auto-labeling
scheme include two stages: first stage is to identify the three
main branches, LAD(LM), LCX and RCA. After that, utilizing
the topological connectivity relationship with the three main
branches, the indexes of sub-branches are identified in the
second stage. We evaluated our method on a private clinical
dataset. Experimental results show that the proposed method
has achieved a satisfactory accuracy for clinical use.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the HBMS IAF-PP - APOLLO
Grant Reference no. : H20c6a0035
This research / project is supported by the National Medical Research Council - N/A
Grant Reference no. : MOH-000358